search for: x86_feature_xmm

...SS and CS /* @@ -692,9 +692,9 @@ ENTRY(simd_coprocessor_error) pushl $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ - ALTERNATIVE "pushl $do_general_protection", \ - "pushl $do_simd_coprocessor_error", \ - X86_FEATURE_XMM + ALTERNATIVE(pushl $do_general_protection, + pushl $do_simd_coprocessor_error, + X86_FEATURE_XMM) #else pushl $do_simd_coprocessor_error #endif diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c7c85724d7e0..49733c72619a 100644 --- a/arch/x86/entry/entry_64.S +...

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl $0,(%%e/rsp) that we use on older CPUs. So let's use the locked variant everywhere - helps keep the code simple as well. While I was at it, I found some inconsistencies in comments in arch/x86/include/asm/barrier.h I hope I'm not splitting this up too much - the reason

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl $0,(%%e/rsp) that we use on older CPUs. So let's use the locked variant everywhere - helps keep the code simple as well. While I was at it, I found some inconsistencies in comments in arch/x86/include/asm/barrier.h I hope I'm not splitting this up too much - the reason

.../ #ifdef CONFIG_X86_32 -/* - * Some non-Intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ - #define mb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory") #define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) #define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) -- MST

...x a584e1c..a65bdb1 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -15,9 +15,12 @@ * Some non-Intel clones support out of order store. wmb() ceases to be a * nop for these. */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \...

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl that we use on older CPUs. So we really should use the locked variant everywhere, except that intel manual says that clflush is only ordered by mfence, so we can't. Note: some callers of clflush seems to assume sfence will order it, so there could be existing bugs around

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl that we use on older CPUs. So we really should use the locked variant everywhere, except that intel manual says that clflush is only ordered by mfence, so we can't. Note: some callers of clflush seems to assume sfence will order it, so there could be existing bugs around

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl that we use on older CPUs. So we really should use the locked variant everywhere, except that intel manual says that clflush is only ordered by mfence, so we can't. Note: some callers of clflush seems to assume sfence will order it, so there could be existing bugs around

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl that we use on older CPUs. So we really should use the locked variant everywhere, except that intel manual says that clflush is only ordered by mfence, so we can't. Note: some callers of clflush seems to assume sfence will order it, so there could be existing bugs around

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl that we use on older CPUs. So let's use the locked variant everywhere. While I was at it, I found some inconsistencies in comments in arch/x86/include/asm/barrier.h The documentation fixes are included first - I verified that they do not change the generated code at all.

mb() typically uses mfence on modern x86, but a micro-benchmark shows that it's 2 to 3 times slower than lock; addl that we use on older CPUs. So let's use the locked variant everywhere. While I was at it, I found some inconsistencies in comments in arch/x86/include/asm/barrier.h The documentation fixes are included first - I verified that they do not change the generated code at all.

...a584e1c..f0d36e2 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -15,15 +15,15 @@ * Some non-Intel clones support out of order store. wmb() ceases to be a * nop for these. */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define mb() asm volatile("lock; addl $0,0(%%esp)":::"memory") #define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) #define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) #else +#def...

...a584e1c..f0d36e2 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -15,15 +15,15 @@ * Some non-Intel clones support out of order store. wmb() ceases to be a * nop for these. */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define mb() asm volatile("lock; addl $0,0(%%esp)":::"memory") #define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) #define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) #else +#def...

The first and third patches are cleaned up versions of an earlier v3 submission by Yang. 1: Nested VMX: check VMX capability before read VMX related MSRs 2: VMX: clean up capability checks 3: Nested VMX: fix IA32_VMX_CR4_FIXED1 msr emulation 4: x86: make hvm_cpuid() tolerate NULL pointers Signed-off-by: Jan Beulich <jbeulich@suse.com>

This changes the pv ops code generation to more closely match reality. For example, instead of: callq *0xffffffff81e3a400 (pv_irq_ops.save_fl) vmlinux will now show: pushfq pop %rax nop nop nop nop nop which is what the runtime version of the code will show in most cases. This idea was suggested by Andy Lutomirski. The benefits are: - For the most common runtime cases

This changes the pv ops code generation to more closely match reality. For example, instead of: callq *0xffffffff81e3a400 (pv_irq_ops.save_fl) vmlinux will now show: pushfq pop %rax nop nop nop nop nop which is what the runtime version of the code will show in most cases. This idea was suggested by Andy Lutomirski. The benefits are: - For the most common runtime cases